ai-podcast-creation

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: References installation guides and supplementary skill configurations from the official inference-sh GitHub organization.
  • [COMMAND_EXECUTION]: Utilizes the infsh command-line utility to perform text-to-speech synthesis, music generation, and media merging.
  • [PROMPT_INJECTION]: Exhibits a surface for indirect prompt injection by ingesting external document content and AI-generated scripts to produce audio narrations.
  • Ingestion points: Processes external document text and generated conversation scripts in SKILL.md.
  • Boundary markers: Lacks explicit delimiters or warnings to ignore embedded instructions in the processed text.
  • Capability inventory: Possesses capabilities to execute shell commands and generate files via the infsh tool.
  • Sanitization: No input validation or content filtering is applied to the text data before it is interpolated into prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 04:25 PM
Security Audit — agent-trust-hub — ai-podcast-creation